Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    news article captions or headlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to visual media or photography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesia
    -0.71
    eele
    -0.70
    nir
    -0.69
    lite
    -0.68
    roth
    -0.67
    sole
    -0.66
    letter
    -0.66
    mare
    -0.66
    abase
    -0.66
    STATE
    -0.64
    POSITIVE LOGITS
     Photos
    0.79
    VERTISEMENT
    0.77
     Deaths
    0.77
    ideos
    0.72
     Faces
    0.68
    natureconservancy
    0.68
     Celeb
    0.66
    etheus
    0.66
    ahl
    0.66
     Moments
    0.65
    Act Density 0.045%

    No Known Activations